ElevenLabs Voice Generator MCP Server

Overview

ElevenLabs Voice Generator allows AI assistants to create high-quality voice audio from text using ElevenLabs' advanced text-to-speech technology. This MCP server provides a bridge between AI assistants and ElevenLabs' voice generation capabilities.

Installation

Prerequisites

• An ElevenLabs API key (obtain from ElevenLabs)
• A voice ID from your ElevenLabs account

Installation Options

Using uvx (Recommended)

The simplest way to install is using uvx:

1. Add the following configuration to your MCP settings file (e.g., cline_mcp_settings.json for Claude Desktop):

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp-server"],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key",
        "ELEVENLABS_VOICE_ID": "your-voice-id",
        "ELEVENLABS_MODEL_ID": "eleven_flash_v2",
        "ELEVENLABS_STABILITY": "0.5",
        "ELEVENLABS_SIMILARITY_BOOST": "0.75",
        "ELEVENLABS_STYLE": "0.1",
        "ELEVENLABS_OUTPUT_DIR": "output"
      }
    }
  }
}

Installing via Smithery

For Claude Desktop users, you can install automatically via Smithery:

npx -y @smithery/cli install elevenlabs-mcp-server --client claude

Manual Installation

For development or custom installations:

1. Clone the repository:

git clone https://github.com/mamertofabian/elevenlabs-mcp-server.git

2. Create a virtual environment:

cd elevenlabs-mcp-server
uv venv

3. Configure your MCP settings file:

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/elevenlabs-mcp-server",
        "run",
        "elevenlabs-mcp-server"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key",
        "ELEVENLABS_VOICE_ID": "your-voice-id",
        "ELEVENLABS_MODEL_ID": "eleven_flash_v2",
        "ELEVENLABS_STABILITY": "0.5",
        "ELEVENLABS_SIMILARITY_BOOST": "0.75",
        "ELEVENLABS_STYLE": "0.1",
        "ELEVENLABS_OUTPUT_DIR": "output"
      }
    }
  }
}

Configuration Options

The server can be configured with the following environment variables:

• ELEVENLABS_API_KEY: Your ElevenLabs API key (required)
• ELEVENLABS_VOICE_ID: Default voice ID to use (required)
• ELEVENLABS_MODEL_ID: Model to use (default: "eleven_flash_v2")
• ELEVENLABS_STABILITY: Voice stability setting (0.0-1.0, default: 0.5)
• ELEVENLABS_SIMILARITY_BOOST: Voice similarity boost (0.0-1.0, default: 0.75)
• ELEVENLABS_STYLE: Voice style setting (0.0-1.0, default: 0.1)
• ELEVENLABS_OUTPUT_DIR: Directory to save audio files (default: "output")

Usage

Once installed and configured, the AI assistant can use the available tools to generate voice audio. The server supports both simple text-to-speech conversion and more complex multi-part scripts with different voices.

Simple Text-to-Speech

For basic voice generation, use the generate_audio_simple tool with your text.

Multi-part Scripts

For more complex scenarios with multiple speakers, use the generate_audio_script tool with a structured script format.

Voice History

The server maintains a history of generated voice audio, which can be accessed and managed using the provided tools.

Web UI Client

The repository also includes a sample SvelteKit MCP Client for testing and demonstration purposes. To use it:

1. Navigate to the web UI directory:

cd clients/web-ui

2. Install dependencies:

pnpm install

3. Copy .env.example to .env and configure as needed

4. Run the web UI:

pnpm dev

5. Open http://localhost:5174/ in your browser